A neural network walks into a lab: towards using deep nets as models for human behavior

TL;DR

This paper explores the potential of deep neural networks as models for human perceptual and cognitive behavior, emphasizing the need for improved evaluation methods and more complex task designs to realize their full utility.

Contribution

It argues for revisiting DNN training and testing cycles from a cognitive science perspective and suggests integrating complex tasks and richer stimuli for better modeling.

Findings

DNNs have potential as models of human behavior.

Current evaluation methods are insufficient.

Complex tasks could enhance model relevance.

Abstract

What might sound like the beginning of a joke has become an attractive prospect for many cognitive scientists: the use of deep neural network models (DNNs) as models of human behavior in perceptual and cognitive tasks. Although DNNs have taken over machine learning, attempts to use them as models of human behavior are still in the early stages. Can they become a versatile model class in the cognitive scientist's toolbox? We first argue why DNNs have the potential to be interesting models of human behavior. We then discuss how that potential can be more fully realized. On the one hand, we argue that the cycle of training, testing, and revising DNNs needs to be revisited through the lens of the cognitive scientist's goals. Specifically, we argue that methods for assessing the goodness of fit between DNN models and human behavior have to date been impoverished. On the other hand, cognitive science might have to start using more complex tasks (including richer stimulus spaces), but doing so might be beneficial for DNN-independent reasons as well. Finally, we highlight avenues where traditional cognitive process models and DNNs may show productive synergy.